harness-engineering

# Harness Engineering <skill_contract> <input>An agent workflow, runtime environment, tools, data sensitivity, effects, cadence, risk, and operator constraints.</input> <output>An auditable runtime kernel with scoped permissions, scheduling, observability, recovery, and eval controls.</output> <done>An end-to-end trace and failure-path tests prove bounded, replayable, recoverable delegated action.</done> <non_goals>Business-task decomposition, prompt-only safety, broad credentials, or unbounded scheduled autonomy.</non_goals> Treat the harness as the kernel around an LLM OS: context is RAM, durable state is disk, tools are system calls, skills are programs, the scheduler is control, and evals are verifiers. Load `references/runtime-control-patterns.md` for matrices and schemas. ## Usage Template Provide: workflow, users, agent roles, environment, tools/connections, data sensitivity, delegated actions, cadence, throughput/SLA, failure history, and risk tolerance. ## Workflow <intake> Run the trace gate: the harness must be able to show what the agent saw, decided, called, changed, and verified. Separate **Agent** (instructions/capabilities), **Environment** (network/files/credentials), and **Session** (mounted context/events/state). Define one auditable control path for high-risk intent and final joins. </intake> <unknowns_gate> If state ownership, credential scope, external side effects, retention, or approval authority is unclear, return `NEEDS_INPUT`. Prob...